sandeepbazar/ocm-mcp-server (sandeepbazar/ocm-mcp-server) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: there is no public source to read and no endpoint we can reach, so there is nothing for us to inspect. No publisher has claimed this listing.
An MCP server that enables AI agents to safely operate multi-cluster Kubernetes fleets through an Open Cluster Management hub, with policy enforcement, human approval, and audit tracing.
Limited view. Automated analysis covers part of this stack. Findings reflect what we verified. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
Limited view: static analysis for Python is partially covered.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
sandeepbazar
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
OCM_MCP_METRICS_PORTno If set, expose Prometheus metrics at /metrics on this port. Default off.OCM_MCP_HOMEno State directory (approval keypair, pending proposals, audit.jsonl, spent-token ids). Default ~/.ocm-mcp.BENCH_HUB_CLUSTERSBENCH_KWOK_SPOKESBENCH_REPSBENCH_PODS_PER_SPOKEBENCH_KWOK_RUNTIMEOCM_MCP_HUB_CONTEXT"": "kind-hub",OCM_MCP_SPOKE_CONTEXTS"": "cluster1=kind-cluster1,cluster2=kind-cluster2,cluster3=kind-cluster3"OCM_MCP_FANOUT_WORKERSno Concurrent spoke scans during get_fleet_health. Default 8 (floor 1).OCM_MCP_MAX_PROPOSAL_BYTESno Reject a proposal larger than this many bytes. Default 262144 (256 KiB).OCM_MCP_MAX_HPA_REPLICASno Reject a HorizontalPodAutoscaler whose maxReplicas exceeds this. Default 100.KUBECONFIGno Kubeconfig file path(s); defaults to ~/.kube/config.OTEL_EXPORTER_OTLP_ENDPOINTexport =http://localhost:4318 # your collectorOCM_MCP_APPROVAL_TTLno Approval-token lifetime in seconds. Default 3600.OCM_MCP_ISSUER/ OCM_MCP_AUDIENCE no Bind approval tokens to this deployment so a token minted elsewhere is refused. Defaults ocm-mcp / ocm-mcp-server.OCM_MCP_AUDIENCEOCM_MCP_ISSUER / no Bind approval tokens to this deployment so a token minted elsewhere is refused. Defaults ocm-mcp / ocm-mcp-server.OCM_MCP_REQUIRE_DIGESTno Set to 1 to require @sha256 digest-pinned images (stricter than tag-pinning). Default off.OCM_MCP_READ_ONLYdestructiveHint and enforced by the gate. Setting =1 turns offOCM_MCP_AUDIT_ECHOOCM_MCP_SIGNER_KEYrecommended Path to the private Ed25519 signing key. Point this off the server (a separate account/device) so a compromised server cannot mint tokens. Default OCM_MCP_HOME/approval_ed25519.OCM_MCP_VERIFIER_KEYno Path to the public verifier key the server loads. Mount read-only. Default OCM_MCP_HOME/approval_ed25519.pub.OCM_MCP_CLIENT_TTLno Seconds before the cached Kubernetes API client is rebuilt, so rotated/refreshed credentials are picked up. Default 600.OCM_MCP_METRICS_HOSTno Interface the metrics endpoint binds. Default 127.0.0.1 (localhost only); set 0.0.0.0 for a remote scraper.OCM_MCP_SPOKE_TIMEOUTno Read timeout (seconds) for spoke health/event/log calls, so one large cluster cannot hang a tool. Default 30.OCM_MCP_HEALTH_LIMITno Max pods/deployments get_cluster_health fetches per cluster; the result notes truncation. Default 500.OCM_MCP_LIST_PAGE_SIZEOCM_MCP_LIST_MAX_ITEMSTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
76/76 tools missing one or more hints — list_clusters (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_clusters (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_cluster (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +73 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
55/76 tool handlers declare input schemas (72%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 14/76 tool handlers wrap calls in try/catch (18%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/sandeepbazar-ocm-mcp-server-1l7531)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check